xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-23 05:35:01 +08:00
Code Issues Packages Projects Releases Wiki Activity
9,167 Commits 155 Branches 89 Tags
Commit Graph

9167 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Isotr0py
d7fbc6ddac
[Misc] Enable V1 FP16 inference on pre-Ampere GPUs (#24022) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-09-01 08:12:22 +00:00
Ning Xie
5438967fbc
[Misc] add hash_function doc string (#24014) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-08-31 23:11:20 -07:00
Code Jesus
422e793fa6
[Bugfix] Add support for <tool_call> format in streaming mode for XLAM Tool Parser (#22769) 
Signed-off-by: Devon Peroutky <devon@kindo.ai>
 2025-09-01 14:07:54 +08:00
Christian Pinto
1cb39dbcdd
[Misc] IO Processor plugins for pooling models (#22820) 
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
 2025-08-31 23:07:12 -07:00
Benji Beck
437c3ce026
Migrate Phi4 inputs to TensorSchema (#23471) 
Signed-off-by: Benji Beck <benjibeck@meta.com>
 2025-09-01 14:05:59 +08:00
Ning Xie
499b074bfd
[Misc] refactor code by import as for torch._inductor.config (#23677) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-09-01 14:05:42 +08:00
Isotr0py
ff0e59d83a
[CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-08-31 22:52:20 -07:00
Woosuk Kwon
b55713683c
[Misc] Move fast prefill logic to separate method (#24013) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-09-01 05:40:38 +00:00
Jun-Howie
acc1a6e10a
Fix the bug related to loading GPTP INT3 weights. (#23328) 
Signed-off-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-09-01 05:39:57 +00:00
Woosuk Kwon
8c742a66d1
[Misc] Avoid redundant copy for encoder-only models (#24012) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-09-01 04:02:43 +00:00
JartX
183a70967a
[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) (#23994) 
Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-09-01 03:33:40 +00:00
Or Ozeri
14b4326b94
v1: Support KV events from connectors (#19737) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2025-09-01 01:13:21 +00:00
Nick Hill
752d2e1c36
[Minor] Fix some random typos in comments (#24009) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-08-31 16:42:17 -07:00
Xiaodong Wang
81eea3d348
vllm fix check on max vocab size (#22471) 
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.me>
 2025-08-31 20:57:05 +08:00
Didier Durand
9701352e4b
[Doc]: fix typos in Python comments (#24001) 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
 2025-08-31 08:21:59 +00:00
Roger Wang
749be00a98
[Core][Multimodal] Allow passing multi_modal_uuids as multimodal identifiers. (#23394) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-08-30 18:01:22 -07:00
Gabriel Marinho
5b8077b8ac
Fix wrong truncate_prompt_tokens type hint (#22761) 
Signed-off-by: Gabriel Marinho <gmarinho@ibm.com>
Signed-off-by: Gabriel Marinho <104592062+gmarinho2@users.noreply.github.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
 2025-08-30 20:39:38 +00:00
Andy Lo
038e9be4eb
[LoRA] Much faster startup when LoRA is enabled (#23777) 
Signed-off-by: Andy Lo <andy@mistral.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-30 15:37:39 +00:00
Ning Xie
68a349114f
[Misc] enhance type hint for rearrange return value (#23519) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-08-30 06:43:33 -07:00
Ning Xie
e80bca309e
[Refactor] refactor freezing_value/cuda_event initialize outside try finally (#23758) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-08-30 06:42:25 -07:00
Ning Xie
fb4983e112
[Misc] add reorder_batch AttentionMetadataBuilder (#23798) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-08-30 06:41:45 -07:00
sadegh.shokatian
379ea2823a
Add LoRA support for DeepSeek models (V2, V3, R1-0528) (#23971) 
Signed-off-by: sadeghja1070 <sadegh.ja1070@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-08-30 06:40:02 -07:00
Jiangyun Zhu
3a6acad431
[Model] Enable encoder DP for MiniCPM-V (#23948) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-08-30 06:31:26 -07:00
Ning Xie
5490d633ce
[UT] fix unify_kv_cache_configs when kv cache config needs sort (#23843) 2025-08-30 11:22:14 +00:00
Jee Jee Li
628d00cd7b
[Bugfix] Fix test_lora_resolvers.py (#23984) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-30 11:16:11 +00:00
Thomas Parnell
4071c76cf3
[V1] [Hybrid] Move MiniMaxLinearAttention into layers/mamba (#23831) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-08-30 00:16:15 -07:00
Cyrus Leung
f1bddbd852
[Core] Cleanup TPU model runner for MM (#23894) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-08-30 00:14:58 -07:00
Yong Hoon Shin
9748c5198b
[CI] Fix broken compile tests due to unsupported SiluMul+Nvfp4Quant fusion (#23973) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-08-30 00:14:43 -07:00
Roger Wang
ee52a32705
[CI] Move testing image from remote URL to S3 (#23980) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-08-29 21:41:25 -07:00
Xin Yang
8fb85b7bb6
Add routed_scaling_factor to MoE grouped topk (#23123) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-08-29 21:36:48 -07:00
dubejf
5b31cb1781
[Bugfix] Fix --config arg expansion called from api_server.py (#23944) 
Signed-off-by: Jean-Francois Dube <dubejf+gh@gmail.com>
Co-authored-by: Jean-Francois Dube <dubejf+gh@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-08-29 21:36:39 -07:00
Roger Wang
d660c98c1b
[CI] Fix unavailable image remote URL (#23966) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-08-29 15:40:04 -07:00
Harry Mellor
5674a40366
[Misc] Make download_weights_from_hf more reliable (#23863) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-29 12:37:24 -07:00
Yong Hoon Shin
8c3e199998
Revert gemma3n fast prefill changes (#23897) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-08-29 12:16:57 -07:00
Thomas Parnell
1c26b42296
[Docs] [V1] [Hybrid] Add new documentation re: contributing mamba-based models (#23824) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-08-29 18:47:58 +00:00
Michael Goin
b7adf94c4a
Tuned H100/H200 triton fp8 block configs for fused_qkv_a_proj (#23939) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-08-29 10:28:35 -07:00
22quinn
4d7fe40fc0
[RL][BugFix] Fix missing tokenizer error for token-in-token-out (#23904) 
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-08-30 01:09:55 +08:00
yzds
0dc9532065
[BUGFIX ] fix undefined silu_and_mul_nvfp4_quant (#23929) 
Signed-off-by: hongchao <hongchao@msh.team>
Signed-off-by: Richard Zou <zou3519@gmail.com>
Co-authored-by: hongchao <hongchao@msh.team>
Co-authored-by: Richard Zou <zou3519@gmail.com>
Co-authored-by: Richard Zou <zou3519@users.noreply.github.com>
 2025-08-29 09:36:39 -07:00
vllmellm
72a69132dc
[CI] Add aiter to matching list of issue auto labeller for rocm tag (#23942) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-08-29 15:29:21 +00:00
Nick Hill
d90d8eb674
[BugFix] Async scheduling and PP compatibility with DP (#23770) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-08-29 08:17:27 -07:00
Lukas Geiger
0a2f4c0793
[Models] Use in-place adds in Idefics2Vision (#23932) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-08-29 07:42:57 -07:00
EduardDurech
1cf3753b90
[MODEL] Apertus and XIELU (#23068) 
Signed-off-by: EduardDurech <39579228+EduardDurech@users.noreply.github.com>
Co-authored-by: AllenHaoHuang <allenhuangdd@gmail.com>
 2025-08-29 20:29:18 +08:00
Adit Chawdhary
4f7cde7272
Adds json_count_leaves utility function (#23899) 
Signed-off-by: aditchawdhary <aditxy@hotmail.com>
 2025-08-29 05:28:13 -07:00
Huy Do
67c14906aa
Update PyTorch to 2.8.0 (#20358) 
Signed-off-by: Huy Do <huydhn@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-08-29 18:57:35 +08:00
Flora Feng
69f46359dd
[Multimodal] Consolidate mm inputs into MultiModalFeatureSpec (#23779) 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
 2025-08-29 18:36:57 +08:00
wang.yuqi
d9e00dbd1f
[Performance] V1 Classify Models E2E Performance Optimization (#23541) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-08-29 03:12:32 -07:00
Li, Jiang
ad39106b16
[CPU] Enable data parallel for CPU backend (#23903) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-08-29 02:19:58 -07:00
Maximilien de Bayser
2554b27baa
[V0 Deprecation] Remove pooling model support in V0 (#23434) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-08-29 00:04:02 -07:00
Harry Mellor
934bebf192
Better errors for Transformers backend missing features (#23759) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-29 07:01:40 +00:00
Jiangyun Zhu
885ca6d31d
[Misc] Fix warnings for mistral model (#23552) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2025-08-29 06:58:48 +00:00